ABSTRACT

The palm vein is one of the most reliable physiological characteristics that can be used to distinguish between individuals. In recent years, it receives more attention from the researchers. In this paper, we present a new approach for the personal identification using palm vein images. This paper attempts to improve the performance of palm vein based verification system with the help of energy feature based on wavelet transform. Energy feature can reflect the wavelet energy distribution of all veins at different resolutions, thus it can efficiently characterize palm veins. Since, wavelet is robust to translation, rotation and distortion. It is also insensitive to contrast changes. From our experimental results, it is found that the proposed scheme outperforms well by achieving higher true acceptance rate and lower false acceptance rate simultaneously. It also demonstrates the power of the proposed approach and more accurate identification. In conclusion, the scheme can improve the identification performance of palm vein recognition significantly.